bot: update RSS feed
This commit is contained in:
github-actions[bot]
32
feed.xml
32
feed.xml
@@ -7,18 +7,18 @@
|
||||
<docs>http://www.rssboard.org/rss-specification</docs>
|
||||
<generator>python-feedgen</generator>
|
||||
<language>en</language>
|
||||
<lastBuildDate>Sun, 22 Feb 2026 00:02:36 +0000</lastBuildDate>
|
||||
<lastBuildDate>Mon, 23 Feb 2026 00:04:10 +0000</lastBuildDate>
|
||||
<item>
|
||||
<title>Hardware Co-Design Scaling Laws via Roofline Modelling for On-Device LLMs</title>
|
||||
<link>https://arxiv.org/abs/2602.10377</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10377.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Luoyang Sun, Jiwen Jiang, Yifeng Ding, Fengfa Li, Yan Song, Haifeng Zhang, Jian Ying, Lei Ren, Kun Zhan, Wei Chen, Yan Xie, Cheng Deng</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Vision-Language-Action Models (VLAs) have emerged as a key paradigm of Physical AI and are increasingly deployed in autonomous vehicles, robots, and smart spaces. In these resource-constrained on-device settings, selecting an appropriate large language model (LLM) backbone is a critical challenge: models must balance accuracy with strict inference latency and hardware efficiency constraints. This makes hardware-software co-design a game-changing requirement for on-device LLM deployment, where each hardware platform demands a tailored architectural solution. We propose a hardware co-design law that jointly captures model accuracy and inference performance. Specifically, we model training loss as an explicit function of architectural hyperparameters and characterise inference latency via roofline modelling. We empirically evaluate 1,942 candidate architectures on NVIDIA Jetson Orin, training 170 selected models for 10B tokens each to fit a scaling law relating architecture to training loss. By coupling this scaling law with latency modelling, we establish a direct accuracy-latency correspondence and identify the Pareto frontier for hardware co-designed LLMs. We further formulate architecture search as a joint optimisation over precision and performance, deriving feasible design regions under industrial hardware and application budgets. Our approach reduces architecture selection from months to days. At the same latency as Qwen2.5-0.5B on the target hardware, our co-designed architecture achieves 19.42% lower perplexity on WikiText-2. To our knowledge, this is the first principled and operational framework for hardware co-design scaling laws in on-device LLM deployment. We will make the code and related checkpoints publicly available.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.10377.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Luoyang Sun, Jiwen Jiang, Yifeng Ding, Fengfa Li, Yan Song, Haifeng Zhang, Jian Ying, Lei Ren, Kun Zhan, Wei Chen, Yan Xie, Cheng Deng</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Vision-Language-Action Models (VLAs) have emerged as a key paradigm of Physical AI and are increasingly deployed in autonomous vehicles, robots, and smart spaces. In these resource-constrained on-device settings, selecting an appropriate large language model (LLM) backbone is a critical challenge: models must balance accuracy with strict inference latency and hardware efficiency constraints. This makes hardware-software co-design a game-changing requirement for on-device LLM deployment, where each hardware platform demands a tailored architectural solution. We propose a hardware co-design law that jointly captures model accuracy and inference performance. Specifically, we model training loss as an explicit function of architectural hyperparameters and characterise inference latency via roofline modelling. We empirically evaluate 1,942 candidate architectures on NVIDIA Jetson Orin, training 170 selected models for 10B tokens each to fit a scaling law relating architecture to training loss. By coupling this scaling law with latency modelling, we establish a direct accuracy-latency correspondence and identify the Pareto frontier for hardware co-designed LLMs. We further formulate architecture search as a joint optimisation over precision and performance, deriving feasible design regions under industrial hardware and application budgets. Our approach reduces architecture selection from months to days. At the same latency as Qwen2.5-0.5B on the target hardware, our co-designed architecture achieves 19.42% lower perplexity on WikiText-2. To our knowledge, this is the first principled and operational framework for hardware co-design scaling laws in on-device LLM deployment. We will make the code and related checkpoints publicly available.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.10377</guid>
|
||||
<pubDate>Tue, 10 Feb 2026 23:51:00 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning</title>
|
||||
<link>https://arxiv.org/abs/2602.13515</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.13515.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jintao Zhang, Kai Jiang, Chendong Xiang, Weiqi Feng, Yuezhou Hu, Haocheng Xi, Jianfei Chen, Jun Zhu</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> Many training-free sparse attention methods are effective for accelerating diffusion models. Recently, several works suggest that making sparse attention trainable can further increase sparsity while preserving generation quality. We study three key questions: (1) when do the two common masking rules, i.e., Top-k and Top-p, fail, and how can we avoid these failures? (2) why can trainable sparse attention reach higher sparsity than training-free methods? (3) what are the limitations of fine-tuning sparse attention using the diffusion loss, and how can we address them? Based on this analysis, we propose SpargeAttention2, a trainable sparse attention method that achieves high sparsity without degrading generation quality. SpargeAttention2 includes (i) a hybrid masking rule that combines Top-k and Top-p for more robust masking at high sparsity, (ii) an efficient trainable sparse attention implementation, and (iii) a distillation-inspired fine-tuning objective to better preserve generation quality during fine-tuning using sparse attention. Experiments on video diffusion models show that SpargeAttention2 reaches 95% attention sparsity and a 16.2x attention speedup while maintaining generation quality, consistently outperforming prior sparse attention methods.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.13515.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jintao Zhang, Kai Jiang, Chendong Xiang, Weiqi Feng, Yuezhou Hu, Haocheng Xi, Jianfei Chen, Jun Zhu</p><p><b>Upvotes:</b> 40</p><p><b>Summary:</b> Many training-free sparse attention methods are effective for accelerating diffusion models. Recently, several works suggest that making sparse attention trainable can further increase sparsity while preserving generation quality. We study three key questions: (1) when do the two common masking rules, i.e., Top-k and Top-p, fail, and how can we avoid these failures? (2) why can trainable sparse attention reach higher sparsity than training-free methods? (3) what are the limitations of fine-tuning sparse attention using the diffusion loss, and how can we address them? Based on this analysis, we propose SpargeAttention2, a trainable sparse attention method that achieves high sparsity without degrading generation quality. SpargeAttention2 includes (i) a hybrid masking rule that combines Top-k and Top-p for more robust masking at high sparsity, (ii) an efficient trainable sparse attention implementation, and (iii) a distillation-inspired fine-tuning objective to better preserve generation quality during fine-tuning using sparse attention. Experiments on video diffusion models show that SpargeAttention2 reaches 95% attention sparsity and a 16.2x attention speedup while maintaining generation quality, consistently outperforming prior sparse attention methods.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.13515</guid>
|
||||
<pubDate>Fri, 13 Feb 2026 23:01:42 +0000</pubDate>
|
||||
</item>
|
||||
@@ -32,21 +32,21 @@
|
||||
<item>
|
||||
<title>Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents</title>
|
||||
<link>https://arxiv.org/abs/2602.16855</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.16855.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haiyang Xu, Xi Zhang, Haowei Liu, Junyang Wang, Zhaozai Zhu, Shengjie Zhou, Xuhao Hu, Feiyu Gao, Junjie Cao, Zihua Wang, Zhiyuan Chen, Jitong Liao, Qi Zheng, Jiahui Zeng, Ze Xu, Shuai Bai, Junyang Lin, Jingren Zhou, Ming Yan</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> The paper introduces GUI-Owl-1.5, the latest native GUI agent model that features instruct/thinking variants in multiple sizes (2B/4B/8B/32B/235B) and supports a range of platforms (desktop, mobile, browser, and more) to enable cloud-edge collaboration and real-time interaction. GUI-Owl-1.5 achieves state-of-the-art results on more than 20+ GUI benchmarks on open-source models: (1) on GUI automation tasks, it obtains 56.5 on OSWorld, 71.6 on AndroidWorld, and 48.4 on WebArena; (2) on grounding tasks, it obtains 80.3 on ScreenSpotPro; (3) on tool-calling tasks, it obtains 47.6 on OSWorld-MCP, and 46.8 on MobileWorld; (4) on memory and knowledge tasks, it obtains 75.5 on GUI-Knowledge Bench. GUI-Owl-1.5 incorporates several key innovations: (1) Hybird Data Flywheel: we construct the data pipeline for UI understanding and trajectory generation based on a combination of simulated environments and cloud-based sandbox environments, in order to improve the efficiency and quality of data collection. (2) Unified Enhancement of Agent Capabilities: we use a unified thought-synthesis pipeline to enhance the model's reasoning capabilities, while placing particular emphasis on improving key agent abilities, including Tool/MCP use, memory and multi-agent adaptation; (3) Multi-platform Environment RL Scaling: We propose a new environment RL algorithm, MRPO, to address the challenges of multi-platform conflicts and the low training efficiency of long-horizon tasks. The GUI-Owl-1.5 models are open-sourced, and an online cloud-sandbox demo is available at https://github.com/X-PLUG/MobileAgent.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.16855.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Haiyang Xu, Xi Zhang, Haowei Liu, Junyang Wang, Zhaozai Zhu, Shengjie Zhou, Xuhao Hu, Feiyu Gao, Junjie Cao, Zihua Wang, Zhiyuan Chen, Jitong Liao, Qi Zheng, Jiahui Zeng, Ze Xu, Shuai Bai, Junyang Lin, Jingren Zhou, Ming Yan</p><p><b>Upvotes:</b> 35</p><p><b>Summary:</b> The paper introduces GUI-Owl-1.5, the latest native GUI agent model that features instruct/thinking variants in multiple sizes (2B/4B/8B/32B/235B) and supports a range of platforms (desktop, mobile, browser, and more) to enable cloud-edge collaboration and real-time interaction. GUI-Owl-1.5 achieves state-of-the-art results on more than 20+ GUI benchmarks on open-source models: (1) on GUI automation tasks, it obtains 56.5 on OSWorld, 71.6 on AndroidWorld, and 48.4 on WebArena; (2) on grounding tasks, it obtains 80.3 on ScreenSpotPro; (3) on tool-calling tasks, it obtains 47.6 on OSWorld-MCP, and 46.8 on MobileWorld; (4) on memory and knowledge tasks, it obtains 75.5 on GUI-Knowledge Bench. GUI-Owl-1.5 incorporates several key innovations: (1) Hybird Data Flywheel: we construct the data pipeline for UI understanding and trajectory generation based on a combination of simulated environments and cloud-based sandbox environments, in order to improve the efficiency and quality of data collection. (2) Unified Enhancement of Agent Capabilities: we use a unified thought-synthesis pipeline to enhance the model's reasoning capabilities, while placing particular emphasis on improving key agent abilities, including Tool/MCP use, memory and multi-agent adaptation; (3) Multi-platform Environment RL Scaling: We propose a new environment RL algorithm, MRPO, to address the challenges of multi-platform conflicts and the low training efficiency of long-horizon tasks. The GUI-Owl-1.5 models are open-sourced, and an online cloud-sandbox demo is available at https://github.com/X-PLUG/MobileAgent.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.16855</guid>
|
||||
<pubDate>Sun, 15 Feb 2026 01:52:19 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.5</title>
|
||||
<link>https://arxiv.org/abs/2602.14457</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.14457.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dongrui Liu, Yi Yu, Jie Zhang, Guanxu Chen, Qihao Lin, Hanxi Zhu, Lige Huang, Yijin Zhou, Peng Wang, Shuai Shao, Boxuan Zhang, Zicheng Liu, Jingwei Sun, Yu Li, Yuejin Xie, Jiaxuan Guo, Jia Xu, Chaochao Lu, Bowen Zhou, Xia Hu, Jing Shao</p><p><b>Upvotes:</b> 24</p><p><b>Summary:</b> To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, Frontier AI Risk Management Framework in Practice presents a comprehensive assessment of their frontier risks. As Large Language Models (LLMs) general capabilities rapidly evolve and the proliferation of agentic AI, this version of the risk analysis technical report presents an updated and granular assessment of five critical dimensions: cyber offense, persuasion and manipulation, strategic deception, uncontrolled AI R\&D, and self-replication. Specifically, we introduce more complex scenarios for cyber offense. For persuasion and manipulation, we evaluate the risk of LLM-to-LLM persuasion on newly released LLMs. For strategic deception and scheming, we add the new experiment with respect to emergent misalignment. For uncontrolled AI R\&D, we focus on the ``mis-evolution'' of agents as they autonomously expand their memory substrates and toolsets. Besides, we also monitor and evaluate the safety performance of OpenClaw during the interaction on the Moltbook. For self-replication, we introduce a new resource-constrained scenario. More importantly, we propose and validate a series of robust mitigation strategies to address these emerging threats, providing a preliminary technical and actionable pathway for the secure deployment of frontier AI. This work reflects our current understanding of AI frontier risks and urges collective action to mitigate these challenges.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.14457.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Dongrui Liu, Yi Yu, Jie Zhang, Guanxu Chen, Qihao Lin, Hanxi Zhu, Lige Huang, Yijin Zhou, Peng Wang, Shuai Shao, Boxuan Zhang, Zicheng Liu, Jingwei Sun, Yu Li, Yuejin Xie, Jiaxuan Guo, Jia Xu, Chaochao Lu, Bowen Zhou, Xia Hu, Jing Shao</p><p><b>Upvotes:</b> 26</p><p><b>Summary:</b> To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, Frontier AI Risk Management Framework in Practice presents a comprehensive assessment of their frontier risks. As Large Language Models (LLMs) general capabilities rapidly evolve and the proliferation of agentic AI, this version of the risk analysis technical report presents an updated and granular assessment of five critical dimensions: cyber offense, persuasion and manipulation, strategic deception, uncontrolled AI R\&D, and self-replication. Specifically, we introduce more complex scenarios for cyber offense. For persuasion and manipulation, we evaluate the risk of LLM-to-LLM persuasion on newly released LLMs. For strategic deception and scheming, we add the new experiment with respect to emergent misalignment. For uncontrolled AI R\&D, we focus on the ``mis-evolution'' of agents as they autonomously expand their memory substrates and toolsets. Besides, we also monitor and evaluate the safety performance of OpenClaw during the interaction on the Moltbook. For self-replication, we introduce a new resource-constrained scenario. More importantly, we propose and validate a series of robust mitigation strategies to address these emerging threats, providing a preliminary technical and actionable pathway for the secure deployment of frontier AI. This work reflects our current understanding of AI frontier risks and urges collective action to mitigate these challenges.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.14457</guid>
|
||||
<pubDate>Mon, 16 Feb 2026 04:30:06 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>World Models for Policy Refinement in StarCraft II</title>
|
||||
<link>https://arxiv.org/abs/2602.14857</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.14857.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yixin Zhang, Ziyi Wang, Yiming Rong, Haoxi Wang, Jinling Jiang, Shuang Xu, Haoran Wu, Shiyu Zhou, Bo Xu</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Large Language Models (LLMs) have recently shown strong reasoning and generalization capabilities, motivating their use as decision-making policies in complex environments. StarCraft II (SC2), with its massive state-action space and partial observability, is a challenging testbed. However, existing LLM-based SC2 agents primarily focus on improving the policy itself and overlook integrating a learnable, action-conditioned transition model into the decision loop. To bridge this gap, we propose StarWM, the first world model for SC2 that predicts future observations under partial observability. To facilitate learning SC2's hybrid dynamics, we introduce a structured textual representation that factorizes observations into five semantic modules, and construct SC2-Dynamics-50k, the first instruction-tuning dataset for SC2 dynamics prediction. We further develop a multi-dimensional offline evaluation framework for predicted structured observations. Offline results show StarWM's substantial gains over zero-shot baselines, including nearly 60% improvements in resource prediction accuracy and self-side macro-situation consistency. Finally, we propose StarWM-Agent, a world-model-augmented decision system that integrates StarWM into a Generate--Simulate--Refine decision loop for foresight-driven policy refinement. Online evaluation against SC2's built-in AI demonstrates consistent improvements, yielding win-rate gains of 30%, 15%, and 30% against Hard (LV5), Harder (LV6), and VeryHard (LV7), respectively, alongside improved macro-management stability and tactical risk assessment.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.14857.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yixin Zhang, Ziyi Wang, Yiming Rong, Haoxi Wang, Jinling Jiang, Shuang Xu, Haoran Wu, Shiyu Zhou, Bo Xu</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Large Language Models (LLMs) have recently shown strong reasoning and generalization capabilities, motivating their use as decision-making policies in complex environments. StarCraft II (SC2), with its massive state-action space and partial observability, is a challenging testbed. However, existing LLM-based SC2 agents primarily focus on improving the policy itself and overlook integrating a learnable, action-conditioned transition model into the decision loop. To bridge this gap, we propose StarWM, the first world model for SC2 that predicts future observations under partial observability. To facilitate learning SC2's hybrid dynamics, we introduce a structured textual representation that factorizes observations into five semantic modules, and construct SC2-Dynamics-50k, the first instruction-tuning dataset for SC2 dynamics prediction. We further develop a multi-dimensional offline evaluation framework for predicted structured observations. Offline results show StarWM's substantial gains over zero-shot baselines, including nearly 60% improvements in resource prediction accuracy and self-side macro-situation consistency. Finally, we propose StarWM-Agent, a world-model-augmented decision system that integrates StarWM into a Generate--Simulate--Refine decision loop for foresight-driven policy refinement. Online evaluation against SC2's built-in AI demonstrates consistent improvements, yielding win-rate gains of 30%, 15%, and 30% against Hard (LV5), Harder (LV6), and VeryHard (LV7), respectively, alongside improved macro-management stability and tactical risk assessment.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.14857</guid>
|
||||
<pubDate>Mon, 16 Feb 2026 15:51:59 +0000</pubDate>
|
||||
</item>
|
||||
@@ -74,7 +74,7 @@
|
||||
<item>
|
||||
<title>Calibrate-Then-Act: Cost-Aware Exploration in LLM Agents</title>
|
||||
<link>https://arxiv.org/abs/2602.16699</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.16699.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenxuan Ding, Nicholas Tomlin, Greg Durrett</p><p><b>Upvotes:</b> 12</p><p><b>Summary:</b> LLMs are increasingly being used for complex problems which are not necessarily resolved in a single response, but require interacting with an environment to acquire information. In these scenarios, LLMs must reason about inherent cost-uncertainty tradeoffs in when to stop exploring and commit to an answer. For instance, on a programming task, an LLM should test a generated code snippet if it is uncertain about the correctness of that code; the cost of writing a test is nonzero, but typically lower than the cost of making a mistake. In this work, we show that we can induce LLMs to explicitly reason about balancing these cost-uncertainty tradeoffs, then perform more optimal environment exploration. We formalize multiple tasks, including information retrieval and coding, as sequential decision-making problems under uncertainty. Each problem has latent environment state that can be reasoned about via a prior which is passed to the LLM agent. We introduce a framework called Calibrate-Then-Act (CTA), where we feed the LLM this additional context to enable it to act more optimally. This improvement is preserved even under RL training of both the baseline and CTA. Our results on information-seeking QA and on a simplified coding task show that making cost-benefit tradeoffs explicit with CTA can help agents discover more optimal decision-making strategies.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.16699.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Wenxuan Ding, Nicholas Tomlin, Greg Durrett</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> LLMs are increasingly being used for complex problems which are not necessarily resolved in a single response, but require interacting with an environment to acquire information. In these scenarios, LLMs must reason about inherent cost-uncertainty tradeoffs in when to stop exploring and commit to an answer. For instance, on a programming task, an LLM should test a generated code snippet if it is uncertain about the correctness of that code; the cost of writing a test is nonzero, but typically lower than the cost of making a mistake. In this work, we show that we can induce LLMs to explicitly reason about balancing these cost-uncertainty tradeoffs, then perform more optimal environment exploration. We formalize multiple tasks, including information retrieval and coding, as sequential decision-making problems under uncertainty. Each problem has latent environment state that can be reasoned about via a prior which is passed to the LLM agent. We introduce a framework called Calibrate-Then-Act (CTA), where we feed the LLM this additional context to enable it to act more optimally. This improvement is preserved even under RL training of both the baseline and CTA. Our results on information-seeking QA and on a simplified coding task show that making cost-benefit tradeoffs explicit with CTA can help agents discover more optimal decision-making strategies.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.16699</guid>
|
||||
<pubDate>Wed, 18 Feb 2026 18:46:14 +0000</pubDate>
|
||||
</item>
|
||||
@@ -88,7 +88,7 @@
|
||||
<item>
|
||||
<title>NeST: Neuron Selective Tuning for LLM Safety</title>
|
||||
<link>https://arxiv.org/abs/2602.16835</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.16835.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sasha Behrouzi, Lichao Wu, Mohamadreza Rostami, Ahmad-Reza Sadeghi</p><p><b>Upvotes:</b> 0</p><p><b>Summary:</b> Safety alignment is essential for the responsible deployment of large language models (LLMs). Yet, existing approaches often rely on heavyweight fine-tuning that is costly to update, audit, and maintain across model families. Full fine-tuning incurs substantial computational and storage overhead, while parameter-efficient methods such as LoRA trade efficiency for inconsistent safety gains and sensitivity to design choices. Safety intervention mechanisms such as circuit breakers reduce unsafe outputs without modifying model weights, but do not directly shape or preserve the internal representations that govern safety behavior. These limitations hinder rapid and reliable safety updates, particularly in settings where models evolve frequently or must adapt to new policies and domains. We present NeST, a lightweight, structure-aware safety alignment framework that strengthens refusal behavior by selectively adapting a small subset of safety-relevant neurons while freezing the remainder of the model. NeST aligns parameter updates with the internal organization of safety behavior by clustering functionally coherent safety neurons and enforcing shared updates within each cluster, enabling targeted and stable safety adaptation without broad model modification or inference-time overhead. We benchmark NeST against three dominant baselines: full fine-tuning, LoRA-based fine-tuning, and circuit breakers across 10 open-weight LLMs spanning multiple model families and sizes. Across all evaluated models, NeST reduces the attack success rate from an average of 44.5% to 4.36%, corresponding to a 90.2% reduction in unsafe generations, while requiring only 0.44 million trainable parameters on average. This amounts to a 17,310x decrease in updated parameters compared to full fine-tuning and a 9.25x reduction relative to LoRA, while consistently achieving stronger safety performance for alignment.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.16835.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Sasha Behrouzi, Lichao Wu, Mohamadreza Rostami, Ahmad-Reza Sadeghi</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Safety alignment is essential for the responsible deployment of large language models (LLMs). Yet, existing approaches often rely on heavyweight fine-tuning that is costly to update, audit, and maintain across model families. Full fine-tuning incurs substantial computational and storage overhead, while parameter-efficient methods such as LoRA trade efficiency for inconsistent safety gains and sensitivity to design choices. Safety intervention mechanisms such as circuit breakers reduce unsafe outputs without modifying model weights, but do not directly shape or preserve the internal representations that govern safety behavior. These limitations hinder rapid and reliable safety updates, particularly in settings where models evolve frequently or must adapt to new policies and domains. We present NeST, a lightweight, structure-aware safety alignment framework that strengthens refusal behavior by selectively adapting a small subset of safety-relevant neurons while freezing the remainder of the model. NeST aligns parameter updates with the internal organization of safety behavior by clustering functionally coherent safety neurons and enforcing shared updates within each cluster, enabling targeted and stable safety adaptation without broad model modification or inference-time overhead. We benchmark NeST against three dominant baselines: full fine-tuning, LoRA-based fine-tuning, and circuit breakers across 10 open-weight LLMs spanning multiple model families and sizes. Across all evaluated models, NeST reduces the attack success rate from an average of 44.5% to 4.36%, corresponding to a 90.2% reduction in unsafe generations, while requiring only 0.44 million trainable parameters on average. This amounts to a 17,310x decrease in updated parameters compared to full fine-tuning and a 9.25x reduction relative to LoRA, while consistently achieving stronger safety performance for alignment.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.16835</guid>
|
||||
<pubDate>Wed, 18 Feb 2026 20:01:01 +0000</pubDate>
|
||||
</item>
|
||||
@@ -109,7 +109,7 @@
|
||||
<item>
|
||||
<title>Discovering Multiagent Learning Algorithms with Large Language Models</title>
|
||||
<link>https://arxiv.org/abs/2602.16928</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.16928.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zun Li, John Schultz, Daniel Hennes, Marc Lanctot</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Much of the advancement of Multi-Agent Reinforcement Learning (MARL) in imperfect-information games has historically depended on manual iterative refinement of baselines. While foundational families like Counterfactual Regret Minimization (CFR) and Policy Space Response Oracles (PSRO) rest on solid theoretical ground, the design of their most effective variants often relies on human intuition to navigate a vast algorithmic design space. In this work, we propose the use of AlphaEvolve, an evolutionary coding agent powered by large language models, to automatically discover new multiagent learning algorithms. We demonstrate the generality of this framework by evolving novel variants for two distinct paradigms of game-theoretic learning. First, in the domain of iterative regret minimization, we evolve the logic governing regret accumulation and policy derivation, discovering a new algorithm, Volatility-Adaptive Discounted (VAD-)CFR. VAD-CFR employs novel, non-intuitive mechanisms-including volatility-sensitive discounting, consistency-enforced optimism, and a hard warm-start policy accumulation schedule-to outperform state-of-the-art baselines like Discounted Predictive CFR+. Second, in the regime of population based training algorithms, we evolve training-time and evaluation-time meta strategy solvers for PSRO, discovering a new variant, Smoothed Hybrid Optimistic Regret (SHOR-)PSRO. SHOR-PSRO introduces a hybrid meta-solver that linearly blends Optimistic Regret Matching with a smoothed, temperature-controlled distribution over best pure strategies. By dynamically annealing this blending factor and diversity bonuses during training, the algorithm automates the transition from population diversity to rigorous equilibrium finding, yielding superior empirical convergence compared to standard static meta-solvers.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.16928.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Zun Li, John Schultz, Daniel Hennes, Marc Lanctot</p><p><b>Upvotes:</b> 6</p><p><b>Summary:</b> Much of the advancement of Multi-Agent Reinforcement Learning (MARL) in imperfect-information games has historically depended on manual iterative refinement of baselines. While foundational families like Counterfactual Regret Minimization (CFR) and Policy Space Response Oracles (PSRO) rest on solid theoretical ground, the design of their most effective variants often relies on human intuition to navigate a vast algorithmic design space. In this work, we propose the use of AlphaEvolve, an evolutionary coding agent powered by large language models, to automatically discover new multiagent learning algorithms. We demonstrate the generality of this framework by evolving novel variants for two distinct paradigms of game-theoretic learning. First, in the domain of iterative regret minimization, we evolve the logic governing regret accumulation and policy derivation, discovering a new algorithm, Volatility-Adaptive Discounted (VAD-)CFR. VAD-CFR employs novel, non-intuitive mechanisms-including volatility-sensitive discounting, consistency-enforced optimism, and a hard warm-start policy accumulation schedule-to outperform state-of-the-art baselines like Discounted Predictive CFR+. Second, in the regime of population based training algorithms, we evolve training-time and evaluation-time meta strategy solvers for PSRO, discovering a new variant, Smoothed Hybrid Optimistic Regret (SHOR-)PSRO. SHOR-PSRO introduces a hybrid meta-solver that linearly blends Optimistic Regret Matching with a smoothed, temperature-controlled distribution over best pure strategies. By dynamically annealing this blending factor and diversity bonuses during training, the algorithm automates the transition from population diversity to rigorous equilibrium finding, yielding superior empirical convergence compared to standard static meta-solvers.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.16928</guid>
|
||||
<pubDate>Wed, 18 Feb 2026 22:41:00 +0000</pubDate>
|
||||
</item>
|
||||
@@ -123,49 +123,49 @@
|
||||
<item>
|
||||
<title>Arcee Trinity Large Technical Report</title>
|
||||
<link>https://arxiv.org/abs/2602.17004</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.17004.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Varun Singh, Lucas Krauss, Sami Jaghouar, Matej Sirovatka, Charles Goddard, Fares Obied, Jack Min Ong, Jannik Straube, Fern, Aria Harley, Conner Stewart, Colin Kealty, Maziyar Panahi, Simon Kirsten, Anushka Deshpande, Anneketh Vij, Arthur Bresnu, Pranav Veldurthi, Raghav Ravishankar, Hardik Bishnoi, DatologyAI Team, Arcee AI Team, Prime Intellect Team, Mark McQuade, Johannes Hagemann, Lucas Atkins</p><p><b>Upvotes:</b> 13</p><p><b>Summary:</b> We present the technical report for Arcee Trinity Large, a sparse Mixture-of-Experts model with 400B total parameters and 13B activated per token. Additionally, we report on Trinity Nano and Trinity Mini, with Trinity Nano having 6B total parameters with 1B activated per token, Trinity Mini having 26B total parameters with 3B activated per token. The models' modern architecture includes interleaved local and global attention, gated attention, depth-scaled sandwich norm, and sigmoid routing for Mixture-of-Experts. For Trinity Large, we also introduce a new MoE load balancing strategy titled Soft-clamped Momentum Expert Bias Updates (SMEBU). We train the models using the Muon optimizer. All three models completed training with zero loss spikes. Trinity Nano and Trinity Mini were pre-trained on 10 trillion tokens, and Trinity Large was pre-trained on 17 trillion tokens. The model checkpoints are available at https://huggingface.co/arcee-ai.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.17004.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Varun Singh, Lucas Krauss, Sami Jaghouar, Matej Sirovatka, Charles Goddard, Fares Obied, Jack Min Ong, Jannik Straube, Fern, Aria Harley, Conner Stewart, Colin Kealty, Maziyar Panahi, Simon Kirsten, Anushka Deshpande, Anneketh Vij, Arthur Bresnu, Pranav Veldurthi, Raghav Ravishankar, Hardik Bishnoi, DatologyAI Team, Arcee AI Team, Prime Intellect Team, Mark McQuade, Johannes Hagemann, Lucas Atkins</p><p><b>Upvotes:</b> 15</p><p><b>Summary:</b> We present the technical report for Arcee Trinity Large, a sparse Mixture-of-Experts model with 400B total parameters and 13B activated per token. Additionally, we report on Trinity Nano and Trinity Mini, with Trinity Nano having 6B total parameters with 1B activated per token, Trinity Mini having 26B total parameters with 3B activated per token. The models' modern architecture includes interleaved local and global attention, gated attention, depth-scaled sandwich norm, and sigmoid routing for Mixture-of-Experts. For Trinity Large, we also introduce a new MoE load balancing strategy titled Soft-clamped Momentum Expert Bias Updates (SMEBU). We train the models using the Muon optimizer. All three models completed training with zero loss spikes. Trinity Nano and Trinity Mini were pre-trained on 10 trillion tokens, and Trinity Large was pre-trained on 17 trillion tokens. The model checkpoints are available at https://huggingface.co/arcee-ai.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.17004</guid>
|
||||
<pubDate>Thu, 19 Feb 2026 01:58:50 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>FRAPPE: Infusing World Modeling into Generalist Policies via Multiple Future Representation Alignment</title>
|
||||
<link>https://arxiv.org/abs/2602.17259</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.17259.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Han Zhao, Jingbo Wang, Wenxuan Song, Shuai Chen, Yang Liu, Yan Wang, Haoang Li, Donglin Wang</p><p><b>Upvotes:</b> 4</p><p><b>Summary:</b> Enabling VLA models to predict environmental dynamics, known as world modeling, has been recognized as essential for improving robotic reasoning and generalization. However, current approaches face two main issues: 1. The training objective forces models to over-emphasize pixel-level reconstruction, which constrains semantic learning and generalization 2. Reliance on predicted future observations during inference often leads to error accumulation. To address these challenges, we introduce Future Representation Alignment via Parallel Progressive Expansion (FRAPPE). Our method adopts a two-stage fine-tuning strategy: In the mid-training phase, the model learns to predict the latent representations of future observations; In the post-training phase, we expand the computational workload in parallel and align the representation simultaneously with multiple different visual foundation models. By significantly improving fine-tuning efficiency and reducing dependence on action-annotated data, FRAPPE provides a scalable and data-efficient pathway to enhance world-awareness in generalist robotic policies. Experiments on the RoboTwin benchmark and real-world tasks demonstrate that FRAPPE outperforms state-of-the-art approaches and shows strong generalization in long-horizon and unseen scenarios.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.17259.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Han Zhao, Jingbo Wang, Wenxuan Song, Shuai Chen, Yang Liu, Yan Wang, Haoang Li, Donglin Wang</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Enabling VLA models to predict environmental dynamics, known as world modeling, has been recognized as essential for improving robotic reasoning and generalization. However, current approaches face two main issues: 1. The training objective forces models to over-emphasize pixel-level reconstruction, which constrains semantic learning and generalization 2. Reliance on predicted future observations during inference often leads to error accumulation. To address these challenges, we introduce Future Representation Alignment via Parallel Progressive Expansion (FRAPPE). Our method adopts a two-stage fine-tuning strategy: In the mid-training phase, the model learns to predict the latent representations of future observations; In the post-training phase, we expand the computational workload in parallel and align the representation simultaneously with multiple different visual foundation models. By significantly improving fine-tuning efficiency and reducing dependence on action-annotated data, FRAPPE provides a scalable and data-efficient pathway to enhance world-awareness in generalist robotic policies. Experiments on the RoboTwin benchmark and real-world tasks demonstrate that FRAPPE outperforms state-of-the-art approaches and shows strong generalization in long-horizon and unseen scenarios.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.17259</guid>
|
||||
<pubDate>Thu, 19 Feb 2026 11:00:46 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Unified Latents (UL): How to train your latents</title>
|
||||
<link>https://arxiv.org/abs/2602.17270</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.17270.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jonathan Heek, Emiel Hoogeboom, Thomas Mensink, Tim Salimans</p><p><b>Upvotes:</b> 27</p><p><b>Summary:</b> We present Unified Latents (UL), a framework for learning latent representations that are jointly regularized by a diffusion prior and decoded by a diffusion model. By linking the encoder's output noise to the prior's minimum noise level, we obtain a simple training objective that provides a tight upper bound on the latent bitrate. On ImageNet-512, our approach achieves competitive FID of 1.4, with high reconstruction quality (PSNR) while requiring fewer training FLOPs than models trained on Stable Diffusion latents. On Kinetics-600, we set a new state-of-the-art FVD of 1.3.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.17270.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Jonathan Heek, Emiel Hoogeboom, Thomas Mensink, Tim Salimans</p><p><b>Upvotes:</b> 32</p><p><b>Summary:</b> We present Unified Latents (UL), a framework for learning latent representations that are jointly regularized by a diffusion prior and decoded by a diffusion model. By linking the encoder's output noise to the prior's minimum noise level, we obtain a simple training objective that provides a tight upper bound on the latent bitrate. On ImageNet-512, our approach achieves competitive FID of 1.4, with high reconstruction quality (PSNR) while requiring fewer training FLOPs than models trained on Stable Diffusion latents. On Kinetics-600, we set a new state-of-the-art FVD of 1.3.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.17270</guid>
|
||||
<pubDate>Thu, 19 Feb 2026 11:18:12 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>ArXiv-to-Model: A Practical Study of Scientific LM Training</title>
|
||||
<link>https://arxiv.org/abs/2602.17288</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.17288.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Anuj Gupta</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> While frontier large language models demonstrate strong reasoning and mathematical capabilities, the practical process of training domain-specialized scientific language models from raw sources remains under-documented. In this work, we present a detailed case study of training a 1.36B-parameter scientific language model directly from raw arXiv LaTeX sources spanning mathematics, computer science, and theoretical physics. We describe an end-to-end pipeline covering metadata filtering, archive validation, LaTeX extraction, text normalization, domain-aware tokenization, and dense transformer training under constrained compute (2xA100 GPUs). Through 24 experimental runs, we analyze training stability, scaling behavior, data yield losses, and infrastructure bottlenecks. Our findings highlight how preprocessing decisions significantly affect usable token volume, how tokenization impacts symbolic stability, and how storage and I/O constraints can rival compute as limiting factors. We further analyze convergence dynamics and show stable training behavior in a data-rich regime (52B pretraining tokens). Rather than proposing a novel architecture, this work provides an engineering-grounded, transparent account of training a small scientific language model from scratch. We hope these insights support researchers operating under moderate compute budgets who seek to build domain-specialized models.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.17288.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Anuj Gupta</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> While frontier large language models demonstrate strong reasoning and mathematical capabilities, the practical process of training domain-specialized scientific language models from raw sources remains under-documented. In this work, we present a detailed case study of training a 1.36B-parameter scientific language model directly from raw arXiv LaTeX sources spanning mathematics, computer science, and theoretical physics. We describe an end-to-end pipeline covering metadata filtering, archive validation, LaTeX extraction, text normalization, domain-aware tokenization, and dense transformer training under constrained compute (2xA100 GPUs). Through 24 experimental runs, we analyze training stability, scaling behavior, data yield losses, and infrastructure bottlenecks. Our findings highlight how preprocessing decisions significantly affect usable token volume, how tokenization impacts symbolic stability, and how storage and I/O constraints can rival compute as limiting factors. We further analyze convergence dynamics and show stable training behavior in a data-rich regime (52B pretraining tokens). Rather than proposing a novel architecture, this work provides an engineering-grounded, transparent account of training a small scientific language model from scratch. We hope these insights support researchers operating under moderate compute budgets who seek to build domain-specialized models.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.17288</guid>
|
||||
<pubDate>Thu, 19 Feb 2026 11:47:30 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>2Mamba2Furious: Linear in Complexity, Competitive in Accuracy</title>
|
||||
<link>https://arxiv.org/abs/2602.17363</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.17363.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gabriel Mongaras, Eric C. Larson</p><p><b>Upvotes:</b> 5</p><p><b>Summary:</b> Linear attention transformers have become a strong alternative to softmax attention due to their efficiency. However, linear attention tends to be less expressive and results in reduced accuracy compared to softmax attention. To bridge the accuracy gap between softmax attention and linear attention, we manipulate Mamba-2, a very strong linear attention variant. We first simplify Mamba-2 down to its most fundamental and important components, evaluating which specific choices make it most accurate. From this simplified Mamba variant (Mamba-2S), we improve the A-mask and increase the order of the hidden state, resulting in a method, which we call 2Mamba, that is nearly as accurate as softmax attention, yet much more memory efficient for long context lengths. We also investigate elements to Mamba-2 that help surpass softmax attention accuracy. Code is provided for all our experiments</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.17363.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Gabriel Mongaras, Eric C. Larson</p><p><b>Upvotes:</b> 7</p><p><b>Summary:</b> Linear attention transformers have become a strong alternative to softmax attention due to their efficiency. However, linear attention tends to be less expressive and results in reduced accuracy compared to softmax attention. To bridge the accuracy gap between softmax attention and linear attention, we manipulate Mamba-2, a very strong linear attention variant. We first simplify Mamba-2 down to its most fundamental and important components, evaluating which specific choices make it most accurate. From this simplified Mamba variant (Mamba-2S), we improve the A-mask and increase the order of the hidden state, resulting in a method, which we call 2Mamba, that is nearly as accurate as softmax attention, yet much more memory efficient for long context lengths. We also investigate elements to Mamba-2 that help surpass softmax attention accuracy. Code is provided for all our experiments</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.17363</guid>
|
||||
<pubDate>Thu, 19 Feb 2026 13:45:23 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Computer-Using World Model</title>
|
||||
<link>https://arxiv.org/abs/2602.17365</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.17365.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiming Guan, Rui Yu, John Zhang, Lu Wang, Chaoyun Zhang, Liqun Li, Bo Qiao, Si Qin, He Huang, Fangkai Yang, Pu Zhao, Lukas Wutschitz, Samuel Kessler, Huseyin A Inan, Robert Sim, Saravan Rajmohan, Qingwei Lin, Dongmei Zhang</p><p><b>Upvotes:</b> 9</p><p><b>Summary:</b> Agents operating in complex software environments benefit from reasoning about the consequences of their actions, as even a single incorrect user interface (UI) operation can derail long, artifact-preserving workflows. This challenge is particularly acute for computer-using scenarios, where real execution does not support counterfactual exploration, making large-scale trial-and-error learning and planning impractical despite the environment being fully digital and deterministic. We introduce the Computer-Using World Model (CUWM), a world model for desktop software that predicts the next UI state given the current state and a candidate action. CUWM adopts a two-stage factorization of UI dynamics: it first predicts a textual description of agent-relevant state changes, and then realizes these changes visually to synthesize the next screenshot. CUWM is trained on offline UI transitions collected from agents interacting with real Microsoft Office applications, and further refined with a lightweight reinforcement learning stage that aligns textual transition predictions with the structural requirements of computer-using environments. We evaluate CUWM via test-time action search, where a frozen agent uses the world model to simulate and compare candidate actions before execution. Across a range of Office tasks, world-model-guided test-time scaling improves decision quality and execution robustness.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.17365.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Yiming Guan, Rui Yu, John Zhang, Lu Wang, Chaoyun Zhang, Liqun Li, Bo Qiao, Si Qin, He Huang, Fangkai Yang, Pu Zhao, Lukas Wutschitz, Samuel Kessler, Huseyin A Inan, Robert Sim, Saravan Rajmohan, Qingwei Lin, Dongmei Zhang</p><p><b>Upvotes:</b> 11</p><p><b>Summary:</b> Agents operating in complex software environments benefit from reasoning about the consequences of their actions, as even a single incorrect user interface (UI) operation can derail long, artifact-preserving workflows. This challenge is particularly acute for computer-using scenarios, where real execution does not support counterfactual exploration, making large-scale trial-and-error learning and planning impractical despite the environment being fully digital and deterministic. We introduce the Computer-Using World Model (CUWM), a world model for desktop software that predicts the next UI state given the current state and a candidate action. CUWM adopts a two-stage factorization of UI dynamics: it first predicts a textual description of agent-relevant state changes, and then realizes these changes visually to synthesize the next screenshot. CUWM is trained on offline UI transitions collected from agents interacting with real Microsoft Office applications, and further refined with a lightweight reinforcement learning stage that aligns textual transition predictions with the structural requirements of computer-using environments. We evaluate CUWM via test-time action search, where a frozen agent uses the world model to simulate and compare candidate actions before execution. Across a range of Office tasks, world-model-guided test-time scaling improves decision quality and execution robustness.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.17365</guid>
|
||||
<pubDate>Thu, 19 Feb 2026 13:48:29 +0000</pubDate>
|
||||
</item>
|
||||
<item>
|
||||
<title>Modeling Distinct Human Interaction in Web Agents</title>
|
||||
<link>https://arxiv.org/abs/2602.17588</link>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.17588.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Faria Huq, Zora Zhiruo Wang, Zhanqiu Guo, Venu Arvind Arangarajan, Tianyue Ou, Frank Xu, Shuyan Zhou, Graham Neubig, Jeffrey P. Bigham</p><p><b>Upvotes:</b> 1</p><p><b>Summary:</b> Despite rapid progress in autonomous web agents, human involvement remains essential for shaping preferences and correcting agent behavior as tasks unfold. However, current agentic systems lack a principled understanding of when and why humans intervene, often proceeding autonomously past critical decision points or requesting unnecessary confirmation. In this work, we introduce the task of modeling human intervention to support collaborative web task execution. We collect CowCorpus, a dataset of 400 real-user web navigation trajectories containing over 4,200 interleaved human and agent actions. We identify four distinct patterns of user interaction with agents -- hands-off supervision, hands-on oversight, collaborative task-solving, and full user takeover. Leveraging these insights, we train language models (LMs) to anticipate when users are likely to intervene based on their interaction styles, yielding a 61.4-63.4% improvement in intervention prediction accuracy over base LMs. Finally, we deploy these intervention-aware models in live web navigation agents and evaluate them in a user study, finding a 26.5% increase in user-rated agent usefulness. Together, our results show structured modeling of human intervention leads to more adaptive, collaborative agents.</p></description>
|
||||
<description><p><img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2602.17588.png" alt="Paper thumbnail" style="max-width: 300px; height: auto;" /></p><p><b>Authors:</b> Faria Huq, Zora Zhiruo Wang, Zhanqiu Guo, Venu Arvind Arangarajan, Tianyue Ou, Frank Xu, Shuyan Zhou, Graham Neubig, Jeffrey P. Bigham</p><p><b>Upvotes:</b> 2</p><p><b>Summary:</b> Despite rapid progress in autonomous web agents, human involvement remains essential for shaping preferences and correcting agent behavior as tasks unfold. However, current agentic systems lack a principled understanding of when and why humans intervene, often proceeding autonomously past critical decision points or requesting unnecessary confirmation. In this work, we introduce the task of modeling human intervention to support collaborative web task execution. We collect CowCorpus, a dataset of 400 real-user web navigation trajectories containing over 4,200 interleaved human and agent actions. We identify four distinct patterns of user interaction with agents -- hands-off supervision, hands-on oversight, collaborative task-solving, and full user takeover. Leveraging these insights, we train language models (LMs) to anticipate when users are likely to intervene based on their interaction styles, yielding a 61.4-63.4% improvement in intervention prediction accuracy over base LMs. Finally, we deploy these intervention-aware models in live web navigation agents and evaluate them in a user study, finding a 26.5% increase in user-rated agent usefulness. Together, our results show structured modeling of human intervention leads to more adaptive, collaborative agents.</p></description>
|
||||
<guid isPermaLink="false">https://arxiv.org/abs/2602.17588</guid>
|
||||
<pubDate>Thu, 19 Feb 2026 18:11:28 +0000</pubDate>
|
||||
</item>
|
||||
|
||||
Reference in New Issue
Block a user